Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 124 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2829. Min Act: -0.0002

Data Index: 897561 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2215. Min Act: -0.0002

Data Index: 118246 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2341. Min Act: -0.0002

Data Index: 632753 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2129. Min Act: -0.0002

Data Index: 959879 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1975. Min Act: -0.0002

Data Index: 240470 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2394. Min Act: -0.0002

Data Index: 438339 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1071. Min Act: -0.0002

Data Index: 274697 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1127. Min Act: -0.0002

Data Index: 1103768 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1100. Min Act: -0.0002

Data Index: 1357366 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1718. Min Act: -0.0002

Data Index: 1228699 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0524. Min Act: -0.0002

Data Index: 840956 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1999. Min Act: -0.0002

Data Index: 782862 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1563. Min Act: -0.0002

Data Index: 664155 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0541. Min Act: -0.0002

Data Index: 1474580 (Python Code)

Max Activating Token Index: 975

Text #14

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1079. Min Act: -0.0002

Data Index: 1654766 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1392. Min Act: -0.0002

Data Index: 1369880 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0798. Min Act: -0.0002

Data Index: 492698 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0790. Min Act: -0.0002

Data Index: 313703 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2259. Min Act: -0.0002

Data Index: 560892 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0073. Min Act: -0.0002

Data Index: 777358 (C4 (Web Text))

Max Activating Token Index: 892